© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 116244
    Prev
    Next
    INDEX
    Explanations

    BP standard, AMA Guides, Back when

    np_acts-logits-general · gemini-2.5-flash-lite

    AI quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     with
    0.66
     as
    0.63
    with
    0.59
    North
    0.58
    s
    0.56
     three
    0.54
     of
    0.53
     North
    0.52
     on
    0.51
     to
    0.50
    POSITIVE LOGITS
    getMainUI
    0.53
     くれ
    0.53
    ា
    0.52
     如何
    0.50
     কপ
    0.50
    لڈ
    0.49
    "+"|".
    0.48
    ನದ
    0.48
     パンツ
    0.47
     incumpl
    0.47
    Activations Density 0.000%

    No Known Activations